Unravelling the Predictive Power of Telematics Data in Car Insurance Pricing

TLDR

A Belgian telematics dataset for young drivers is used to explore how car insurance premiums can be designed based on black‑box collected driving behaviour, contrasting traditional models that rely on self‑reported variables such as age and postal code, which are only indirectly related to accident risk. The study aims to quantify and interpret how telematics variables affect expected claim frequency using generalized additive models and compositional predictors. The authors employ generalized additive models with compositional predictors to model the effect of telematics data on claim frequency. The analysis shows that telematics variables improve predictive power and render gender an unnecessary rating variable.

Abstract

Summary A data set from a Belgian telematics product aimed at young drivers is used to identify how car insurance premiums can be designed based on the telematics data collected by a black box installed in the vehicle. In traditional pricing models for car insurance, the premium depends on self-reported rating variables (e.g. age and postal code) which capture characteristics of the policy(holder) and the insured vehicle and are often only indirectly related to the accident risk. Using telematics technology enables tailor-made car insurance pricing based on the driving behaviour of the policyholder. We develop a statistical modelling approach using generalized additive models and compositional predictors to quantify and interpret the effect of telematics variables on the expected claim frequency. We find that such variables increase the predictive power and render the use of gender as a rating variable redundant.